# Inkling-Small vs Llama 3.2 1B

> Inkling-Small is the stronger model overall, scoring 46.5 to 19.9 on the Noometry Index. Llama 3.2 1B costs 9.0× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-small-vs-llama-3-2-1b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Llama 3.2 1B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 7.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 0.6% for Llama 3.2 1B.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 60K.

## Snapshot

| | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| Provider | Thinking Machines Lab | Meta |
| Noometry Index | 46.5 | 19.9 |
| Rank | 57 | 349 |
| Context | 524K | 60K |
| Input $/M | $0.45 | $0.027 |
| Output $/M | $1.20 | $0.20 |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.3 (#80)
- Llama 3.2 1B: 20.6 (#333)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 1451 | 1071 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
| BigCodeBench Instruct | — | 8.2% |
| BigCodeBench Complete | — | 11.3% |

## Agentic & Tool Use

- Inkling-Small: —
- Llama 3.2 1B: 14.5 (#142)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10.8% |
| BALROG | — | 6.6% |

## Reasoning

- Inkling-Small: 39.0 (#53)
- Llama 3.2 1B: 15.6 (#304)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| Chess Puzzles | 18% | 0% |
| LMArena Hard Prompts | 1424 | 1044 |
| Epoch Capabilities Index | 150.13 | 101.95 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Mystery Game Puzzles | 6% | — |

## Math

- Inkling-Small: 44.9 (#65)
- Llama 3.2 1B: 9.7 (#308)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 0.6% |
| LMArena Math | 1453 | 1086 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |

## Knowledge

- Inkling-Small: 48.3 (#71)
- Llama 3.2 1B: 7.2 (#307)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 88.5% | 23.9% |
| LMArena Expert | 1442 | 1007 |
| SimpleQA Verified | 19.1% | — |

## Multimodal

- Inkling-Small: 38.4 (#59)
- Llama 3.2 1B: —

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#102)
- Llama 3.2 1B: 23.9 (#287)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1400 | 973 |
| LMArena Chinese | 1458 | 958 |
| LMArena German | 1412 | 1014 |
| LMArena Russian | 1392 | 941 |
| LMArena French | 1438 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1355 | — |
| LMArena Spanish | 1426 | — |

## Instruction Following

- Inkling-Small: 73.9 (#112)
- Llama 3.2 1B: 52.6 (#285)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1031 |

## Long Context

- Inkling-Small: 42.7 (#113)
- Llama 3.2 1B: 31.9 (#269)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1401 | 1050 |

## Writing & Preference

- Inkling-Small: 59.8 (#102)
- Llama 3.2 1B: 21.4 (#305)

| Benchmark | Inkling-Small | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1413 | 1055 |
| LMArena Creative Writing | 1330 | 1033 |
| EQ-Bench Creative Writing | 1491 | 200 |
| LMArena Multi-Turn | 1420 | 1030 |

## FAQ

### Is Inkling-Small better than Llama 3.2 1B?

Inkling-Small is the stronger model overall, scoring 46.5 to 19.9 on the Noometry Index. Llama 3.2 1B costs 9.0× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, Inkling-Small or Llama 3.2 1B?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Inkling-Small or Llama 3.2 1B better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 20.6 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 60K.

### How many benchmarks do Inkling-Small and Llama 3.2 1B share?

18 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Llama 3.2 1B has 22.